Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    repeated or blank spaces in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code or configuration file fragments

    np_acts-logits-general · gemini-2.0-flash

    assignment statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    l
    -0.57
    -
    -0.56
    V
    -0.55
    v
    -0.54
     
    -0.54
    G
    -0.53
     and
    -0.52
    b
    -0.51
     –
    -0.50
    L
    -0.50
    POSITIVE LOGITS
    protoimpl
    1.29
     мәкал
    1.28
    ConstraintMaker
    1.24
     سكانية
    1.19
     autorytatywna
    1.18
    OGND
    1.18
    tagHelperRunner
    1.17
    ArrowToggle
    1.17
    verwijspagina
    1.16
     дописавши
    1.16
    Act Density 0.489%

    No Known Activations